How to Write Better AI Prompts: 4-Part Framework

Sheridan Wendt (00:00)
AI it's not magic It's not magic. It responds based on how clearly you communicate right bad Some of you may have heard bad input bad output right bad data in bad data out

Here's a bad prompt. Write a marketing plan for my business.

Jon Foster (00:17)
⁓ yeah, I mean, there's not enough information there. It's good. It's bound to fail. Yeah, that's a good. That's a good bad one.

Sheridan Wendt (00:24)
Super vague, right? Super vague. So here's how you take that and make it a good prompt, right?

Jon Foster (00:25)
Mm-hmm.

Sheridan Wendt (00:30)
Welcome to the AI Advantage podcast. I'm your host Sheridan Wint, and I've got my friend Jon Foster here. And we're going to be talking about how to talk to AI and get better results, also known as prompt engineering. You may have heard of prompt engineering before.

Jon Foster (00:45)
little of the experience that yesterday when we asked Chad GPT and Gemini and I the two different things and once we rephrased it I can definitely see how this is going to be helpful.

Sheridan Wendt (00:54)
Yeah, yeah, yeah. That was on our last episode. I think it's episode four in the series, where we did a side by side of Gemini and Chat GPT to create an image of Florida man. And in honor of that image, Jon is dressed like Florida man today.

Ha ha ha ha!

Jon Foster (01:12)
Get on get.

Sheridan Wendt (01:13)
All right, so digging into why prompting matters

AI it's not magic It's not magic. It responds based on how clearly you communicate right bad Some of you may have heard bad input bad output right bad data in bad data out

It's the same thing when you're prompting a model right any model

Good prompts, better results, less editing, way more accuracy. You put any funny prompts in, Jon, that you got some crazy outputs on?

Jon Foster (01:44)
⁓ mine, my favorite is when I misspell things. Cause I type too fast or my phone's just too small. I don't know what it is. And then something completely what I did not ask comes up and I'm like, ⁓

Sheridan Wendt (01:56)
Yeah. Usually the spelling, usually for me, I haven't seen like a spelling thing. Usually it's like, I know what you meant. And it just keeps on going. Must be misspelling some. There's some words though that you move one or two letters around and the whole meaning of the word changes. ⁓

Jon Foster (01:56)
Yeah.

man.

Yep, like, ⁓ like, ⁓ like duck.

Sheridan Wendt (02:15)
like duck.

How would you rearrange duck?

Jon Foster (02:18)
I mean, you click one key to the right, you're in a little bit of trouble.

Sheridan Wendt (02:19)
⁓ I see.

I see, I see. Got you. Typo. Typo. All right. So let's talk about prompts, right? What actually is a prompt? Any ideas?

Jon Foster (02:36)
a prompt. Well, I would assume it would be setting the AI up for, you know, a request of information that you, whatever you put in. So input.

Sheridan Wendt (02:49)
is input, yeah, it's anything, any input that you give it. So a good way to structure your prompt are instructions and then context and then your desired outcome, right? Instructions plus context plus desired outcome equals a good prompt.

Right? So you want to, it tends to work best like any given model, right? AI tends to work best when it knows who it's writing for, what you want, how you want it delivered, and what good looks like, right? What you expect. So we're going to dive in to a four-part framework, which we touched a little bit on, but it's going to sound a little different, right? Number one, the role or the perspective, right?

Act as a marketing strategist, or act as a customer support expert, or act as a mad scientist from 1970. And then give it the context. What's the goal? Who's the audience? What problem are we solving? Give it a little bit of context.

Well, we'll get into some examples here in a minute, right? So number one, we got the role and the perspective. Number two, we've got context. Number three, we've got task. What exactly do you want it to do? And number four, the format, right? Do you need bullet points? Do you need a script? Do you need an email, a table? Do you need steps, a blog article? What is it, right? So we're going to talk about some good prompts and some bad prompts and just do a little comparison, right?

Jon Foster (04:12)
Okay.

Sheridan Wendt (04:13)
Can you give me a bad prompt?

Jon Foster (04:15)
⁓ I could probably do that all day.

Sheridan Wendt (04:17)
Let's go.

Jon Foster (04:19)
No, I can't. Not on the spot. I thought I could. I failed you.

Sheridan Wendt (04:20)
All

right, all right, a bad prompt.

Here's a bad prompt. Write a marketing plan for my business.

Jon Foster (04:29)
⁓ yeah, I mean, there's not enough information there. It's good. It's bound to fail. Yeah, that's a good. That's a good bad one.

Sheridan Wendt (04:36)
Super vague, right? Super vague. So here's how you take that and make it a good prompt, right?

Jon Foster (04:37)
Mm-hmm.

Sheridan Wendt (04:41)
Let's go back and look at our four part prompt framework, right? Role, task, and format. So you are a marketing strategist, right? That's the role.

Jon Foster (04:46)
Instruction.

Mm-hmm.

Sheridan Wendt (04:57)
Helping a small real estate team struggling with lead consistency. That's some context. The task, create a 30 day marketing plan focused on email nurturing and social content.

Jon Foster (05:03)
Mm-hmm.

Sheridan Wendt (05:11)
and then the format. Format it as a weekly checklist.

So that's going to put out something way better than write a marketing plan for my business.

Jon Foster (05:20)
100%. So a bad prompt.

Sheridan Wendt (05:22)
Give me another bad prompt.

We can walk through another example again together.

Jon Foster (05:29)
where can I buy a shirt?

Sheridan Wendt (05:31)
Where can I buy your shirt? Definitely a shirt.

Jon Foster (05:33)
Where can I buy a shirt? A shirt.

Not just any shirt.

Sheridan Wendt (05:37)
Where can I buy a shirt? Yeah, definitely. You don't know what you're gonna get with that one, right?

Jon Foster (05:42)
No, not at all.

Sheridan Wendt (05:44)
So role, let's go through it. What's a role? What's the person's role?

or perspective.

Jon Foster (05:49)
from the perspective of...

What was the name for somebody that's in the fashion? so in the role of someone who was up to date on today's fashion.

Sheridan Wendt (05:59)
Okay.

Jon Foster (06:00)
Would that be a good start? Would that be a good roll? Or would you improve that?

Sheridan Wendt (06:05)
Yeah, mean, you could say a model, as a fashion model.

Jon Foster (06:08)
mean, that's the thing, like, my thing is like I overthink things and I'm like, the fashion model wouldn't do it, they just put, they just wear the clothes.

Sheridan Wendt (06:15)
but you want to buy the fashionable clothes, right?

Jon Foster (06:18)
Yeah, but a fashion designer, let's say that. As a fashion designer.

Sheridan Wendt (06:20)
Okay, as a fashion designer and then con-

and then context.

Jon Foster (06:26)
And then pick out a shirt that would look good this season.

Sheridan Wendt (06:31)
Okay, let's season it.

Jon Foster (06:32)
based

on

the recent fashion week event that just happened

Sheridan Wendt (06:37)
Okay. I thought you meant like fall, summer, spring, winter, but fashion season. I got it. I got it.

Jon Foster (06:43)
No,

Sheridan Wendt (06:46)
I thought you meant weather seasons. ⁓

Here's what we got so far.

Role number one, as a fashion designer, to the context, what problem are we solving? I need to find a new shirt to wear to an event. Task, find me a shirt and explain the event, right? Maybe is it like a black tie event? Is it a ball? Is it just a kickback at somebody's house? Is it like a at?

Jon Foster (07:11)
Okay.

Yeah.

Sheridan Wendt (07:25)
So you want to give it that context, what kind of event is it? And then the task, find me a shirt that I can wear that's blue.

Jon Foster (07:35)
Yeah, OK. So even if the problem has not as much information, you've got to kind of add more detail into it to be able to generate the better results. I'm assuming.

Sheridan Wendt (07:37)
and

Yeah, yeah. So here's another way we could do it, right? ⁓ As a fashion model, find me, I need a, as a fashion model, that's the role, I need a blue dress for a cocktail party. That's the context. Task, find me a blue dress I can wear. And then the format, provide this as a list of

Jon Foster (08:04)
Mm.

Sheridan Wendt (08:12)
URLs where I can go look at the dresses.

Jon Foster (08:17)
Okay

Sheridan Wendt (08:18)
Now you can shorten that up a little bit too. You could say, as a fashion model, I need a blue dress for a cocktail party. Provide me with a list of dress options. Right? Now that last sentence, you put the task and the format in the same sentence, right? The task is give me a list of dresses and the format is a list, right? Of dresses though. So yeah, so it doesn't have to be crazy. You can kind of combine a lot of that stuff, but basically the more information you give it.

Jon Foster (08:40)
Yeah.

Sheridan Wendt (08:48)
better result you're going to get.

Yep, yep, yep, All right, prompting mistakes, common prompting mistakes. Being too vague, right? Give me a business plan. Well, we need to know what business it is and what you're planning for, right? What do you sell? All of that good stuff. What are your services? What are your offerings? What's your budget? Asking for too much at once, right? Asking for it to give you a plan.

for how you're going to get from a high school graduate to landing on the moon with just your own money, your own budget. Right? It might give you some sort of plan, but it's gonna be pretty tough to execute because it will lack a lot of details, right?

Jon Foster (09:25)
Mmm.

Sheridan Wendt (09:33)
Another common mistake, leaving out the audience, right? Telling it to generate something, but not telling the model who the intended audience is. Who's gonna read it? Who's gonna look at this thing?

Another common mistake, forgetting to specify the tone, right? You want to say is it going to be friendly, right? Let's say you're drafting an email, is it supposed to be professional, is it supposed to be friendly, is it supposed to be authoritative, you know, what kind of tone do you want it to have? Examples, right? Not giving examples, that's another common mistake.

Jon Foster (10:00)
Okay.

Sheridan Wendt (10:05)
it gets much better if you give it an example and say, here I'm looking for a JSON file structured in this particular way, right? And if you give it the example, well, the example should have all the values, all the keys in it that you're looking for, right? So then it can say, OK, well, let me just replace the values and keep all the keys and your output will be structured exactly like probably you wanted it to be because you gave it an example.

Another common mistake is not telling it, you know, not telling the model what you don't want it to do, right? Don't format this as HTML. Don't, right, don't give me a list of texts, give me a list of hyperlinks, right? So you're telling it what not to do and what to do. Another common mistake is not iterating enough, right?

Jon Foster (10:39)
Mm-hmm.

Sheridan Wendt (10:53)
first response that you get from a model, not always the best response, but you can modify it, you can adjust it, it's a conversation, right? It's not like a one-off request.

Jon Foster (10:55)
Mm-hmm.

So when you're saying you have to ask it a multitude of times or just a couple times about the same thing, redundancy?

Sheridan Wendt (11:09)
Bye.

Not always, but if you don't like the response that you get and you want it to be better, you can tell it exactly in what way you want it to be better. So let's say in our example earlier, it gives us a list of dresses and it says, you know, this dress by this designer, this dress by that designer, right? Dress number three by designer number three. And it's just giving you list of text. Well, that's not what you wanted. What you wanted was a list of links, hyperlinks that you can click on and then it opens it up.

in ⁓ Sephora or I don't know some fashion brand I have no idea so if it gives you not what you wanted then you can just say hey format this you know I like to actually just put the word output with a colon instead of having to say format it like this I just put output colon list of urls right very brief

Jon Foster (12:03)
Okay.

And what is what is that by doing that? What is that? What does that do specifically?

Sheridan Wendt (12:09)
Well, instead of giving you a list that says, you know, this blue dress by designer one, this blue dress by designer two, instead it will literally just give you a list of hyperlinks you can click on.

Jon Foster (12:20)
Okay, so but but the the colon adding the colon in there and stuff like that, is that is that a key to all the non-it people?

Sheridan Wendt (12:30)
So I like to, let's say we're talking about context, we're talking about giving it more information, better data in, better data out. Pro tip that I like to do is I'll just write a single sentence or question, but I give it context within the question. Let me go, let me pull up an example and just go look at something recently that I did.

Jon Foster (12:37)
Mm-hmm.

Mm.

Sheridan Wendt (12:53)
Alright, so I wanted to...

you find it.

I was working on a growth plan for a client and I put in a sentence that says, output this...

with formatting instead of markdown, right? And so it's one sentence, output this as formatting instead of markdown, which it might sound like a bad prompt, right? But in between those two words where I said, this, after this, I put parentheses, and inside the parentheses, I put like a massive amount of text. It's like 10 or 12 paragraphs, and it's all written in

Markdown format and all I wanted it to do was give me To actually give it to me as bold right because it gave it to me in plain text so when you look at the text it's like Star star star week one star star star and that makes it bold right? And I didn't want all that in there, so I just wrote a sentence. said output this with the formatting instead of in markdown and I put all of that text in parentheses

Jon Foster (13:41)
Hmm.

Mm-mm.

Sheridan Wendt (13:58)
in there so it knows what text I'm talking about and it knows that I don't want it to look like that right I want it so parentheses I use all over the place I'll use a colon I might say if I'm building a website I might say make these make the following changes colon right and then parentheses and I'll put all the changes in there and then close the parentheses and put a period and then I might also give it some more to do

Jon Foster (14:04)
Yeah.

Mm-hmm.

Sheridan Wendt (14:26)
Although you could probably put all of the changes within the parentheses. ⁓

Jon Foster (14:30)
when you

say markdown like for for the non-it people what does that mean

Also me, because I don't know.

Sheridan Wendt (14:37)
So Markdown is just like a format, a syntax. It just...

I don't know. Let me ask Chad JBT to explain it better than I can.

I probably should give you a different example, a way more simple example.

Jon Foster (14:50)
Show us an example of a good problem for solving this problem.

Sheridan Wendt (14:54)
So.

Let's see.

So let me give you an example using the colon and the parentheses, right? Back to our fashion designer, right? Let's say that they, let's say that they are our fashion model. Let's say that we made the prompt like this, help me find a dress that meets these requirements and doesn't look like it's been bedazzled and wasn't in this list of dresses, right? And so that's like one sentence.

Jon Foster (15:03)
Mm-hmm.

you

Sheridan Wendt (15:21)
It's like one run-on sentence. But if you use parentheses in there, in the right places, then you can give it much better requirements. So let's start a new chat here. I'll share my screen.

Jon Foster (15:34)
So like, putting like things like no sequins and other little details that go in the dresses that you do not want. Like, you don't want shiny, sparkly, you want something more matte. Okay.

Sheridan Wendt (15:46)
Yeah, yeah, yeah.

Find me a-

provide, let's do it this way, as a fashion model.

provide me a list of dresses that meet these requirements, parentheses, right? That I can wear to a cocktail party.

Make sure it doesn't have any of these features.

Jon Foster (16:15)
Parentheses.

Sheridan Wendt (16:16)
and wasn't isn't on this list of dresses from last year right so in the requirements here i might say

Jon Foster (16:29)
Mm-hmm.

Sheridan Wendt (16:33)
Blue.

sleek not fluffy right no has lace i don't know i don't know i'm not not really into dresses so i'm just making this up as i go but

Jon Foster (16:47)
Just mini skirts.

Sheridan Wendt (16:49)
Yeah, mini skirts. ⁓ Covers the knees, right? Let's keep it classy. Covers the knees. That I can wear to a cocktail

Jon Foster (16:58)
Knee length,

yeah.

Sheridan Wendt (17:01)
⁓ yeah, we'll put is at least knee length.

⁓ make sure doesn't have any these features sequence i'm probably gonna spell that wrong but whatever ⁓

Jon Foster (17:11)
I have no idea. Actually, I think you spelled it right, but I'm not sure.

Sheridan Wendt (17:15)
bedazzled.

glitter. Alright, doesn't have any of that and is not on this list of dresses from last year. We'll say...

Jon Foster (17:19)
You did.

Sheridan Wendt (17:25)
I don't know anything about dresses. ⁓ Not from this list of brands. We'll do that. So no Nike dresses, no Adidas.

Jon Foster (17:38)
Jimmy Choo, Versace, you know.

Sheridan Wendt (17:41)
No,

yeah, sure, no Versace. So anyway, so we just put all of that into parentheses. So now this prompt, looks pretty long, but it's really just a sentence, know, find me the dress that meets these requirements that I can wear to a cocktail party. Two sentences, make sure it doesn't have any of these features, right? And isn't on this list of brands. So that's very specific. Now it's gonna give me a list.

Jon Foster (17:47)
Actually, does Versace even make glasses?

Sheridan Wendt (18:07)
right? And it's probably, I don't know if they'll have URLs or not.

I'm curious how this is going to go. Looking and address recommendation.

focusing on reputable retailers. It's telling us how it's thinking. Look at this. ⁓ All these sites that it's ⁓ searching.

Jon Foster (18:19)
Mm.

Sheridan Wendt (18:24)
double check that they don't have sequins or glitter. It's very cool, man. You can see the thought process it's going through.

Jon Foster (18:31)
Yeah, that is extremely neat.

Hmm.

Sheridan Wendt (18:34)
It's said it came across some dresses that it's not sure if it has it but that brand typically does have some sparkly stuff going on so it's just gonna stay away from that brand.

Jon Foster (18:44)
Okay.

Sheridan Wendt (18:45)
Searching some more. Saks Fifth Avenue.

Jon Foster (18:48)
Okay.

Sheridan Wendt (18:49)
Here we go, it says each product page is going to be cited.

All right, it's giving a list of dresses and a description of why that dress meets the requirements, and there's a URL.

Jon Foster (19:01)
Dope.

Sheridan Wendt (19:02)
So we have five dresses here. Now I can say output.

list of URLs only.

is maybe I want to email this to somebody, right?

Jon Foster (19:11)
Okay, yeah.

Sheridan Wendt (19:12)
So now we're iterating on the prompt. We're telling it exactly what output we want.

thinking. All right, there's the URLs.

Write this as write this list as an email to a

Fashion model friend So we're just iterating on what it came out with and now here we go now It basically did everything for us. It drafted the email. It says hey friend's name, right? We didn't tell it our friend's name I've been scouting some cocktail ready dresses and found a bunch that I think you'll like Blue sleek lace knee-length or longer completely free of sequins glitter and bedazzling perfect for a chic evening

Jon Foster (19:53)
And like that, we now know where to go get dresses.

Sheridan Wendt (19:57)
I'm sure

everybody was super interested in that. ⁓

Jon Foster (20:02)
I mean.

It is 2025.

Sheridan Wendt (20:04)
Ladies, here you go. The top one on here is self, number one is self portrait by blue fine lace midi dress. no, maybe that brand is self portrait. Anyways, dress.

Jon Foster (20:17)
I shop

at Nordstrom, so there's one by my house.

Sheridan Wendt (20:21)
Yeah. All let me stop sharing.

Sheridan Wendt (20:23)
All right, let me stop sharing. So anyway, that's some examples of how you can make your prompts better, how you can avoid some of the mistakes. Let's do some, there's some templates. Some people actually sell these templates. I don't think that's necessary for you to do that. You can just ask AI to help you create it into a better prompt, right? But if you wanna go buy templates, feel free, go buy them. Maybe we'll put some on the website, who knows? I think it's a little, I think it's a, I

seems to me it's like... huh.

Jon Foster (20:50)
I'm curious.

What happens if we ask AI? say, like, yeah, like, like, how can I, how can I best format my questions for you to help me?

Sheridan Wendt (20:56)
give you the prompt

So there's a cool setting in a lot of these models. A chat GPT, for example, you can go into the settings and you can say preferences, right? And you can tell it, you know, talk to me like a five-year-old, right? You can also say, if I don't give you enough information, ask a clarifying question, right? Or ask clarifying questions if you don't have enough information. Another thing I like to do is I'll use one model to...

draft a prompt and put it into a different model. So let's say I'm like building a website and I'm using AI to like build a whole web app or something. I'll format all of it. Like I'll get it all ready to go in and say like Claude or ChatGBT and say, help me create a prompt for this tool that I'm using to build a website. I want the website to have to meet these requirements, right? I want it to match my brand. I want it to align with my tone and you've got to tell it, you these are my brand colors.

Jon Foster (21:35)
Mm-hmm.

Sheridan Wendt (21:56)
and this is the tone I use. Here's some, I'll go to a website and grab all the text on the website and say, here's my existing website and everything that is on there now, right? And, you know, build out a site map. I want it to have these pages, contact us and, you know, features and offerings. And so you just put all that and then chat GPT or whatever model you're using will spit out a prompt. And you can take that and put it in the other one and it'll build out the whole website, the whole app for you.

Jon Foster (22:24)
That's nuts. That's crazy. Is it able to verify its own creation? Like, is it able to like, you know how when you create a website and everything like that, like the contact us button isn't mapped correctly, you know, and it doesn't, you know, is it able to check on itself?

Sheridan Wendt (22:39)
Some of the models can, yeah. Some of the tools can. One of the ones I use, it'll test it, right? It'll do like, when you do a software development cycle, got dev, test, QA maybe, ⁓ or UAT, and then production, right? Everybody's, all the organizations tend to have their own way that they do those, but this tool that I use, will.

Jon Foster (22:41)
That's crazy.

Mm.

Sheridan Wendt (23:04)
it will develop it and then it will test it make sure that it works and then i'll say okay it's ready to go and publish it

Jon Foster (23:11)
That is that is amazing because I was I was just thinking in my head and everything like one of the biggest things and one of the hardest things that I experienced when learning this and stuff like that was like user friendliness. You know, you could probably like ask AI and be like from, you know, the perspective of a web developer. Um, make input, whatever the website or whatever. What would you suggest to make this more user friendly?

Sheridan Wendt (23:12)
Yes, sir.

Yeah.

Jon Foster (23:40)
And then, you know, maybe a little bit more context sprinkled in, but you know, it probably tell you exactly how to do it. That's crazy.

Sheridan Wendt (23:48)
It would, it would.

All right, with that, I think that's a good point for us to hear a quick message from our friends and sponsors, and we'll be right back after this.

Answer Engines: How Brands Build the AI Advantage (23:58)
Right now, AI is deciding who your next customer trusts, and it might not be you. You might not realize it yet, but ChatGPT, Gemini, Perplexity, all of these models are already deciding who they choose to recommend in industries like yours. And they don't always list options either. Sometimes they give one answer. And if that answer isn't you, then AI just referred your ideal customer to your competitor.

That's why we created the free AI Visibility Review. It's a short live session where we will sit down with you and show you what AI thinks of you and your brand and your company, who it thinks is an authority, and what you can do to become the authority that it starts to recommend. Don't just guess where you stand. Find out. Schedule your free AI Visibility Review today at advantagelabs.ai and see if AI knows that your business exists.

Imagine what it would do for your business if chat GPT was actually referring people to you. Advantage Labs . AI, your AI advantage.

Sheridan Wendt (25:06)
And we're back. This is the AI Advantage podcast. I'm your host, Sheridan, and we were just talking about prompt engineering, specifically how do you talk to AI and get better results. The next thing that we were gonna go through were some ideas for how to do different things with your prompts, right?

Jon Foster (25:25)
Okay, let's get into it.

Sheridan Wendt (25:27)
Let's get into it. First up, brainstorming, right? Give me 10 ideas for blank, right? You know, it's a good way to start a prompt. Give me 10 ideas for this or let them give me 10, give me 100, give me 50, whatever, right? Give it a number. Another thing that you can do is rewrite, right? Rewrite this to be clearer, shorter, more casual, that kind of thing. Obviously you gotta put the context in there of what you want it to rewrite.

But we're not going to get into the whole prompt. We're just going to give you real quick some ideas on how you can start off a prompt. Summarization. Summarize this as a bullet point list. Turn this into a step-by-step workflow. If you want to create a standard operating procedure, create a process, turn this into a step-by-step workflow. Comparisons. Compare option A and B. I do this a lot. I'll say compare and contrast.

the these two softwares or these two products I'm thinking about buying, right? And give me like, give me a well, that's all I'll say I say compare and contrast these. Yeah. Well, yeah, it'll it'll do that on its own, but you can also specify like, you know, I'm concerned about the price or I'm I really want to make sure I have this feature, right? So you can get that context in there, but I use it a lot.

Jon Foster (26:22)
Mm-mm.

Frozen Cons List

Sheridan Wendt (26:42)
for comparing things.

All right, now onto the power of iteration. We talked about that a little bit earlier ⁓ the example that we did with the dress, right? Iterating on that prompt. So just a few things when you get some output and it's not exactly what you want, just tell it how it can be exactly what you want.

Jon Foster (26:51)
Mm-hmm.

Sheridan Wendt (27:00)
Right? Make it friendlier, make it shorter, make it more concise. Give me three variations to pick from or give it an example. A lot of times the second prompt is better than the first or the second output is better than the first as well.

Jon Foster (27:14)
and we learned that on the dresses part now for sure i agree to that

Sheridan Wendt (27:19)
Yeah, yeah, yeah. And we learned it with Florida Man.

Now let's say that you are getting an output that you don't like, right? And you did everything you can think of. You used the four part prompt framework, right? You did the role, the role or perspective, the context, the task and the format. You did all of that and you iterated on it and it's still coming out bad and you don't like the output, right? A simple thing you can do is say, what information do you need from me to finish this, right? What do you need from me? What details do you need from me to make this better?

Jon Foster (27:30)
Mm.

Sheridan Wendt (27:51)
You can just ask it and see what it says. Maybe it needs some details that have not been provided yet.

Jon Foster (27:57)
Yeah, I like that feature for sure. Cause especially like, you mean, you, know what you want something and you need it done, but you don't know exactly how to, how to, how to phrase it. You know what I mean? And that kind of gives you like a guideline to where you can like level it out. Yeah. I like that.

Sheridan Wendt (28:14)
Yeah, yes, sir. All right, I think that about does it for today. A few takeaways from today's episode. A good prompt is clarity plus context plus constraints. That's a good prompt. We've got the four prompt framework here that anyone can reference.

any time. We're going to have a blog article about that that you can check out. That'll be a link in the description. Something to think about, AI is your partner. Think of it like a junior team member that can help you out. And I'd like to challenge you to go try a few prompts today. It's free. You can try a lot of these tools for free. Go try them out, see what you can do, and let us know how it goes. All right. Well, take care. This is Sheridan and signing off. See you on the next episode of

the AI Advantage podcast.